-
Notifications
You must be signed in to change notification settings - Fork 0
/
get_cbs.py
262 lines (194 loc) · 12.6 KB
/
get_cbs.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
!/usr/bin/env python
##################################################################################################################################################
# #
# This script performs a complete basis set (CBS) extrapolation from CCSD(T)/cc-pVTZ and CCSD(T)/cc-pVQZ single point energies. #
# The relevant data is extracted from output files generated by the ORCA programm. #
# -> CCSD(T)/cc-pVTZ single points must end with "_TZ.out" #
# -> CCSD(T)/cc-pVQZ single points must end with "_QZ.out" #
# #
# Relevant data will be generated in a .txt file (cbs_data.txt)! #
# #
# Version: 1.03 #
# #
# Author: Fabian L. Zott #
# Last modified: 16.06.2021 #
# #
##################################################################################################################################################
import pandas as pd
import os
import glob
import sys
import re
import fileinput
import shutil # for copying files
import pathlib
import math
pd.options.display.float_format = '{:10.6f}'.format
################################################# Some Variables ###############################################################################
criteria = float(0.026255) # kJ/mol
criteria_hartree = float(0.00001) # energy criteria in Hartree 0.0000099999992
hartconv = float(2625.498) # conversion factor of [Hartree] to [kJ/mol]
R = float(0.008314511) # gas constant as [kJ/K*mol]
temp = float(289.15) # standard condition temperature
kcalvonv = float(4184) # conversion factor [kcal] to [kJ/mol]
elemDict = {"1" : "H", "2" : "He", "3" : "Li", "4" : "Be", "5" : "B", \
"6" : "C", "7" : "N", "8" : "O", "9" : "F", "10" : "Ne", \
"11" : "Na" , "12" : "Mg" , "13" : "Al" , "14" : "Si" , "15" : "P", \
"16" : "S" , "17" : "Cl" , "18" : "Ar" , "19" : "K" , "20" : "Ca", \
"21" : "Sc" , "22" : "Ti" , "23" : "V" , "24" : "Cr" , "25" : "Mn", \
"26" : "Fe" , "27" : "Co" , "28" : "Ni" , "29" : "Cu" , "30" : "Zn", \
"31" : "Ga" , "32" : "Ge" , "33" : "As" , "34" : "Se" , "35" : "Br", \
"36" : "Kr" , "37" : "Rb" , "38" : "Sr" , "39" : "Y" , "40" : "Zr", \
"41" : "Nb" , "42" : "Mo" , "43" : "Tc" , "44" : "Ru" , "45" : "Rh", \
"46" : "Pd" , "47" : "Ag" , "48" : "Cd" , "49" : "In" , "50" : "Sn", \
"51" : "Sb" , "52" : "Te" , "53" : "I" , "54" : "Xe" , "55" : "Cs", \
"56" : "Ba" , "57" : "La" , "58" : "Ce" , "59" : "Pr" , "60" : "Nd", \
"61" : "Pm" , "62" : "Sm" , "63" : "Eu" , "64" : "Gd" , "65" : "Tb", \
"66" : "Dy" , "67" : "Ho" , "68" : "Er" , "69" : "Tm" , "70" : "Yb", \
"71" : "Lu" , "72" : "Hf" , "73" : "Ta" , "74" : "W" , "75" : "Re", \
"76" : "Os" , "77" : "Ir" , "78" : "Pt" , "79" : "Au" , "80" : "Hg", \
"81" : "Tl" , "82" : "Pb" , "83" : "Bi" , "84" : "Po" , "85" : "At", \
"86" : "Rn" , "87" : "Fr" , "88" : "Ra" , "89" : "Ac" , "90" : "Th", \
"91" : "Pa" , "92" : "U" , "93" : "Np" , "94" : "Pu" , "95" : "Am", \
"96" : "Cm" , "97" : "Bk" , "98" : "Cf" , "99" : "Es" ,"100" : "Fm", \
"101": "Md" ,"102" : "No" ,"103" : "Lr" ,"104" : "Rf" ,"105" : "Db", \
"106": "Sg" ,"107" : "Bh" ,"108" : "Hs" ,"109" : "Mt" ,"110" : "Ds", \
"111": "Rg" ,"112" : "Uub","113" : "Uut","114" : "Uuq","115" : "Uup", \
"116": "Uuh","117" : "Uus","118" : "Uuo"}
######################## Functions ##############################################################################################
def getSinglePointEnergyFromORCA(file) :
f = open(file) # Open file on read mode
dataList = f.read().split("\n") # Create a list containing all lines
f.close()
#print(dataList)
for index, value in enumerate(dataList): # fill datalist
if 'FINAL SINGLE POINT ENERGY' in value:
#print(index, value)
index = int(index)
E_tot_DPLNO = value.split()[4] # get energy value by splitting line by whitespace and returning 4th value
#print(E_tot_DPLNO)
return E_tot_DPLNO
def completeBasisSet(file_TZ, file_QZ) :
#################### some variables for CBS extrapolation ##########################
alfa = float(-5.46)
beta = float(3.05)
n = 3
m = 4
f = open(file_TZ) # open file on read mode
dataList_TZ = f.read().split("\n") # create a list containing all lines
f.close()
for index, value in enumerate(dataList_TZ): # fill datalist
if 'Reference energy' in value:
#print(index, value)
index = int(index)
RefTZ = float(value.split()[3]) # get energy value by splitting line by whitespace and returning 3rd value
if 'Final correlation energy' in value:
#print(index, value)
index = int(index)
CorrTZ = float(value.split()[4]) # get energy value by splitting line by whitespace and returning 4th value
#print("Reference energy TZ:", RefTZ)
#print("Final correlation energy TZ", CorrTZ)
f = open(file_QZ) # open file on read mode
dataList_QZ = f.read().split("\n") # create a list containing all lines
f.close()
for index, value in enumerate(dataList_QZ): # fill datalist
if 'Reference energy' in value:
#print(index, value)
index = int(index)
RefQZ = float(value.split()[3]) # get energy value by splitting line by whitespace and returning 3rd value
if 'Final correlation energy' in value:
#print(index, value)
index = int(index)
CorrQZ = float(value.split()[4]) # get energy value by splitting line by whitespace and returning 4th value
#print("Reference energy QZ:", RefQZ)
#print("Final correlation energy QZ", CorrQZ)
########################## Extrapolating to CBS #####################################
corrAlfaN = (math.exp(alfa * math.sqrt(n)))/1
corrAlfaM = (math.exp(alfa * math.sqrt(m)))/1
RE_extrapolated = ((RefTZ * corrAlfaM) - (RefQZ * corrAlfaN))/(corrAlfaM - corrAlfaN)
Corr_extrapolated = (((n ** beta) * CorrTZ) - ((m ** beta) * CorrQZ))/((n ** beta)-(m ** beta))
SCF_E_extrapolated = RE_extrapolated + Corr_extrapolated
return SCF_E_extrapolated
#########################Prepare Folder for Execution of GetData####################
directory_in_str = str(os.getcwd())
directory = os.fsencode(directory_in_str)
current_dir = pathlib.Path.cwd()
parent_dir = current_dir.parent
############################ Save Methode code as string #######################################################
for file in os.listdir(directory):
filename = os.fsdecode(file)
if filename.endswith("_TZ.out"): #-------------------------------------------
method_code_TZ = "_TZ" #
file_end_TZ = "_TZ.out" # !! common filnames for DPLNO QZ and TZ!!
elif filename.endswith("_QZ.out"): #
method_code_QZ = "_QZ" #
file_end_QZ = "_QZ.out" #-------------------------------------------
else:
print("No specific file extension found in:", filename)
################################## Extracting TZ Total Energy from .out ########################################
data_TZ = pd.DataFrame(columns=["Structure","E_tot_DPLNO(TZ)"])
for file in os.listdir(directory):
filename = os.fsdecode(file)
if any(filename.endswith(file_end_TZ) for file in os.listdir('.')):
#print("ORCA-DPLNO-TZ Calculation found!!")
#data_opt = pd.DataFrame(columns=["Structure","E_tot_B3LYP_SMD"])
filename = os.fsdecode(file)
basename = str(os.path.splitext(filename)[0])
E_tot_DPLNO_TZ = getSinglePointEnergyFromORCA(file)
#print("Out:", E_tot_DPLNO_TZ)
data_TZ = data_TZ.append({'Structure': basename, 'E_tot_DPLNO(TZ)': E_tot_DPLNO_TZ}, ignore_index=True)
#data_opt = data_opt.append({'E_tot_B3LYP_SMD': E_tot}, ignore_index=True)
data_TZ = data_TZ.replace(method_code_TZ, '',regex=True)
#print(data_TZ)
################################## Create Empty Dataframe ######################################################
data = data_TZ.copy()
data = data[['Structure']]
################################## Extracting QZ Total Energy from .out ########################################
data_QZ = pd.DataFrame(columns=["Structure","E_tot_DPLNO(QZ)"])
for file in os.listdir(directory):
filename = os.fsdecode(file)
if any(filename.endswith(file_end_QZ) for file in os.listdir('.')):
#print("ORCA-DPLNO-QZ Calculation found!!")
#data_opt = pd.DataFrame(columns=["Structure","E_tot_B3LYP_SMD"])
filename = os.fsdecode(file)
basename = str(os.path.splitext(filename)[0])
E_tot_DPLNO_QZ = getSinglePointEnergyFromORCA(file)
#print("Out:", E_tot_DPLNO_QZ)
data_QZ = data_QZ.append({'Structure': basename, 'E_tot_DPLNO(QZ)': E_tot_DPLNO_QZ}, ignore_index=True)
#data_opt = data_opt.append({'E_tot_B3LYP_SMD': E_tot}, ignore_index=True)
data_QZ = data_QZ.replace(method_code_QZ, '',regex=True)
#print(data_QZ)
############################# Extrapolating Complete Basis Set for DPLNO #######################################
data_CBS = pd.DataFrame(columns=["Structure","E_tot_DPLNO(CBS)"])
for file in os.listdir(directory):
filename = os.fsdecode(file)
if any(filename.endswith(file_end_TZ) for file in os.listdir('.')):
filename = os.fsdecode(file)
basename_TZ = str(os.path.splitext(filename)[0])
basename = basename_TZ.replace("_TZ", "")
basename_QZ_out = basename + "_QZ.out"
basename_QZ = basename_QZ_out.replace(".out", "")
print("-----------------------next----------------------------")
print("CBS extraplolation for", basename_TZ, "and", basename_QZ)
SCF_E_extrapolated = completeBasisSet(file, basename_QZ_out) #where first is TZ (as "file" in for loop) second is corresponding QZ!!!!
data_CBS = data_CBS.append({'Structure': basename, 'E_tot_DPLNO(CBS)': SCF_E_extrapolated}, ignore_index=True)
print("E_tot_CBS:", SCF_E_extrapolated)
#data_CBS = data_CBS.replace(method_code_QZ, '',regex=True)
#print(data_CBS)
################################# Merge all Dataframes and print ###############################################
data = pd.merge(data, data_TZ, on="Structure")
data = pd.merge(data, data_QZ, on="Structure")
data = pd.merge(data, data_CBS, on="Structure")
print("\n")
print("\n")
print("\n")
print("\n")
print("\n")
print("\n")
print(data)
print("\n")
print("\n")
print("\n")
#print(data.info())
data.to_csv(r'./cbs_data.txt', sep='\t', header='true', index=False, index_label=False, na_rep='NULL')
print("------------------------Code run smoothly!!------------------------")